Share via

Submit document blob path to Azure Document Intelligence service?

Dilip Jain 20 Reputation points
2025-12-11T05:43:10.44+00:00

I'm using the Azure AI Document Intelligence Python SDK (azure-ai-documentintelligence) to analyze documents stored in Azure Blob Storage. My current workflow involves:

  1. Downloading the document from Blob Storage to my application
  2. For large documents (100+ pages), splitting the PDF into chunks in memory
  3. Sending each chunk's bytes to the Document Intelligence service

Question:

  1. Can I pass an Azure Blob URL directly to begin_analyze_document for single document analysis instead of downloading and uploading the file bytes? I'd like to provide a blob URL (with SAS token or Managed Identity) and have Document Intelligence fetch the document directly.
  2. Does the service support page range parameters (e.g., pages="1-100") so I can analyze specific pages without splitting the PDF myself? This would allow me to process a long document in ranges without downloading/chunking.
  3. Is there a single-document equivalent to AzureBlobContentSource used in batch processing? I know begin_analyze_batch_documents supports blob sources, but it seems like overkill for single document analysis.Is it possible to directly pass the Azure Blob Storage URL/path to the Document Intelligence service instead of downloading and uploading the file content? I want to avoid the intermediate step of fetching the blob content to my application before sending it to Document Intelligence.
Azure AI Document Intelligence
0 comments

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. Q&A Assist
    2025-12-11T05:43:45.81+00:00
    AI generated content. This question contains an answer created with AI from Q&A Assist. Learn more
    1. Passing Azure Blob URL: Currently, the Azure AI Document Intelligence service does not support passing an Azure Blob URL directly to begin_analyze_document for single document analysis. You need to download the document and then send the bytes to the service.
    2. Page Range Parameters: The service does not explicitly mention support for page range parameters (e.g., pages="1-100"). Therefore, you would need to split the PDF yourself into chunks before sending them for analysis.
    3. Single-Document Equivalent to AzureBlobContentSource: There is no direct equivalent to AzureBlobContentSource for single document analysis. The batch processing method begin_analyze_batch_documents is designed for multiple documents, and it is indeed more suited for batch operations rather than single document analysis.

    In summary, you will need to handle the downloading and chunking of documents manually before sending them to the Document Intelligence service.

    0 comments

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.